Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/cklxx/elephant.ai/kaku-runtime-test)<a href="https://agentmods.dev/commands/cklxx/elephant.ai/kaku-runtime-test"><img src="https://agentmods.dev/badge/commands/cklxx/elephant.ai/kaku-runtime-test.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.01456 |
| Opus 5 | $0.00000 | $0.00728 |
| Sonnet 5 | $0.00000 | $0.00291 |
| Haiku 4.5 | $0.00000 | $0.00146 |
Grade A, and why
kaku-runtime-test scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s http://localhost:9090/api/runtime/sessions | jq '.[].state' How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/kaku-runtime-test — Kaku Runtime 集成测试
测试 Agent 用 Kaku 管理编程团队的完整端到端流程。 起点永远是 inject(模拟飞书消息),不直接调用内部 CLI。
参数: $ARGUMENTS(可选,如 TC-1、TC-2 TC-4;不填则全跑)
测试场景概览
Agent 收到飞书消息后,通过 kaku-runtime skill 在 Kaku pane 中启动 CC/Codex 编程团队, 监控其执行,在卡住时介入,最终汇报结果。测试验证这整条链路。
用户飞书消息(inject)
↓
Agent(LLM + kaku-runtime skill)
↓ kaku cli split-pane → CC/Codex 启动
Kaku pane(TR 区域)
↓ CC 执行工具 → PostToolUse hook → notify_runtime.sh
runtime bus(:9090/api/hooks/runtime)
↓ heartbeat / stalled / completed 事件
StallDetector(60s 无心跳)→ LeaderAgent(决策:INJECT/FAIL)
↓
飞书通知(completed/failed)
Step 0 — 建立四宫格布局(独立新窗口)
# 新窗口建四宫格(不与用户当前窗口重叠)
eval $(bash scripts/kaku/layout.sh 4grid \
--new-window \
--cwd /Users/bytedance/code/elephant.ai \
| grep -E "TOP_RIGHT|BOT_LEFT|BOT_RIGHT" \
| awk '{print "export "$0}')
# BL:实时日志(runtime bus 事件 + 工具调用)
bash scripts/kaku/send.sh --pane-id $BOT_LEFT \
"tail -f ~/code/elephant.ai/logs/alex-service.log | grep -E 'runtime_bus_event|TaskExecution|leader'"
┌──────────────────────┬──────────────────────┐
│ TL: Claude (当前) │ TR: CC team panes │
│ 测试结果在此汇报 │ agent splits here │
├──────────────────────┼──────────────────────┤
│ BL: 日志监控 │ BR: (空闲) │
│ runtime_bus_event │ │
└──────────────────────┴──────────────────────┘
Step 1 — 运行测试
# 告知测试脚本:CC session 应 split 自 TR pane
KAKU_PARENT_PANE=$TOP_RIGHT \
bash scripts/test/kaku-runtime-e2e.sh $ARGUMENTS 2>&1 | tee /tmp/kaku-e2e-$(date +%H%M).log
测试用例
| TC | 场景 | 关键验证 |
|---|---|---|
| TC-0 | 基础设施健康检查 | HTTP 200 + bus 事件 + session API |
| TC-1 | 单 Agent 写文件 | 新 pane 出现 + heartbeat + 文件存在 |
| TC-2 | 两个 Agent 并行 | 2 个不同 session_id + 2 个新 pane |
| TC-3 | A→B 依赖任务链 | 两文件存在,B 晚于 A 的 completed |
| TC-4 | Stall + LeaderAgent | type=stalled + LeaderAgent 决策日志 |
| TC-5 | 查询团队状态 | reply 含 session 状态信息 |
| TC-6 | 分析→实现→验证 | 3 个 session_id + 3 个输出文件 |
| TC-7 | 手动注入恢复卡住的 session | agent 使用 session inject 命令 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 7d ago First seen · 148 lines · 0 tokens per session scan A 2d32fa97c54c
kaku-runtime-test is a command published in the GitHub repository cklxx/elephant.ai (11 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,456 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
paul:verify
Guide manual user acceptance testing of recently built features.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
ui-snapshot.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
journey-audit
Outside-in product audit as a deep session — 7 read-only roles check what the site promises against what the code does, what a user experiences, what arrives by mail, and what the data says is used. Writes a dossier; needs a per-repo journey-manifest.
laravel-playwright
E2E Playwright patterns; use the laravel:e2e-playwright skill exactly as written.
qa
Smoke or browser-walk a running app. Report only. Do not implement. Do not merge.